Run predictions from state-of-the-art machine learning models right from your browser. Use intuitive GUIs, no preprocessing or coding required! You can upload your own models here by logging into your Gradio account with GitHub and uploading a GitHub repository.
Is a Green Screen Really Necessary for Real-Time Portrait Matting?
A demo of Noise2Same, an image denoising method developed by Yaochen Xie et al. and presented in NeurIPS 2020.
This is a demo of Background Matting V2. This model requires both a source image and a background image.
A NeurIPS 2020 paper by Wang et al. Outperforms the state-of-the-art methods by a large margin on four challenging crowd counting datasets
This is an interface implementation for "Object-Centric Learning with Slot Attention", trained on the CLVER dataset.
A demo of Inception Net, along with many examples where it does not predict the correct class.
NUBIA stands for "NeUral Based Interchangeability Assessor". NUBIA gives a score on a scale of 0 to 1 reflecting how much it thinks the candidate text is interchangeable with the reference text.
A super resolution model. Try it with your low resolution images now!
This model, RNA-GPS, is trained on APEX-seq data, which measures RNA localization within human HEK293T cells.
In this interface, the user inputs apical-4-chamber images from echocardiography videos and the model will output a prediction of the localization of the left ventricle in blue.
nussl (pronounced "nuzzle") is a flexible, object oriented Python audio source separation library created by the Interactive Audio Lab at Northwestern University
A simple pdf to audio converter.